DANSK and DaCy 2.6.0: Domain Generalization of Danish Named Entity Recognition

no code implementations • 28 Feb 2024 • Kenneth Enevoldsen, Emil Trenckner Jessen, Rebekah Baglini

Named entity recognition is one of the cornerstones of Danish NLP, essential for language technology applications within both industry and research.

Domain Generalization named-entity-recognition +2

Augmenty: A Python Library for Structured Text Augmentation

no code implementations • 9 Dec 2023 • Kenneth Enevoldsen

Augmnety is a Python library for structured text augmentation.

Dependency Parsing named-entity-recognition +4

Danish Foundation Models

no code implementations • 13 Nov 2023 • Kenneth Enevoldsen, Lasse Hansen, Dan S. Nielsen, Rasmus A. F. Egebæk, Søren V. Holm, Martin C. Nielsen, Martin Bernstorff, Rasmus Larsen, Peter B. Jørgensen, Malte Højmark-Bertelsen, Peter B. Vahlstrup, Per Møldrup-Dalum, Kristoffer Nielbo

Large language models, sometimes referred to as foundation models, have transformed multiple fields of research.

TextDescriptives: A Python package for calculating a large variety of metrics from text

1 code implementation • 5 Jan 2023 • Lasse Hansen, Ludvig Renbo Olsen, Kenneth Enevoldsen

TextDescriptives is a Python package for calculating a large variety of metrics from text.

DaCy: A Unified Framework for Danish NLP

no code implementations • 12 Jul 2021 • Kenneth Enevoldsen, Lasse Hansen, Kristoffer Nielbo

In addition, we conduct a series of tests for biases and robustness of Danish NLP pipelines through augmentation of the test set of DaNE.

Data Augmentation Dependency Parsing +4